NUBOT: Embedded Knowledge Graph With RASA Framework for Generating Semantic Intents Responses in Roman Urdu

TL;DR

This paper presents a method to generate accurate intents from Roman Urdu data and integrates a knowledge graph with the RASA framework to improve chatbot understanding and response accuracy.

Contribution

It introduces embedding a knowledge graph into RASA for semantic intent recognition in Roman Urdu, reducing reliance on extensive labeled datasets.

Findings

Minimum intent accuracy of 64% confidence

Response generation accuracy of 82.1%

Maximum accuracy gain of 96.7%

Abstract

The understanding of the human language is quantified by identifying intents and entities. Even though classification methods that rely on labeled information are often used for the comprehension of language understanding, it is incredibly time consuming and tedious process to generate high propensity supervised datasets. In this paper, we present the generation of accurate intents for the corresponding Roman Urdu unstructured data and integrate this corpus in RASA NLU module for intent classification. We embed knowledge graph with RASA Framework to maintain the dialog history for semantic based natural language mechanism for chatbot communication. We compare results of our work with existing linguistic systems combined with semantic technologies. Minimum accuracy of intents generation is 64 percent of confidence and in the response generation part minimum accuracy is 82.1 percent and maximum accuracy gain is 96.7 percent. All the scores refers to log precision, recall, and f1 measure for each intents once summarized for all. Furthermore, it creates a confusion matrix represents that which intents are ambiguously recognized by approach.